{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/extractive-document-summarization","name":"Extractive Text Summarization","slug":"extractive-document-summarization","description_markdown":"Given a document, selecting a subset of the words or sentences which best represents a summary of the document.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":95,"papers_with_code":34,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/extractive-document-summarization-on-cnn","slug":"extractive-document-summarization-on-cnn","dataset":"CNN / Daily Mail","dataset_url":"/dataset/cnn-daily-mail-1","rows_in_archive":15,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"HAHSum","paper_title":"Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network","paper_url":"/paper/neural-extractive-summarization-with","paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/extractive-document-summarization-on","slug":"extractive-document-summarization-on","dataset":"DebateSum","dataset_url":"/dataset/debatesum","rows_in_archive":3,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"Longformer-Base","paper_title":"DebateSum: A large-scale argument mining and summarization dataset","paper_url":"/paper/debatesum-a-large-scale-argument-mining-and","paper_date":"2020-11-14","arxiv_id":"2011.07251","code_links":[{"title":"Hellisotherpeople/DebateSum","url":"https://github.com/Hellisotherpeople/DebateSum"},{"title":"arvind-balaji/debate-cards","url":"https://github.com/arvind-balaji/debate-cards"},{"title":"Hellisotherpeople/debate2vec","url":"https://github.com/Hellisotherpeople/debate2vec"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debatesum-a-large-scale-argument-mining-and#ran","syntology_url":"https://syntology.ai/paper/2011.07251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07251"}},"official":{"repos":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/extractive-text-summarization-on-govreport","slug":"extractive-text-summarization-on-govreport","dataset":"GovReport","dataset_url":"/dataset/govreport","rows_in_archive":2,"metrics":["Avg. Test Rouge1","Avg. Test Rouge2","Avg. Test RougeLsum"],"first_row_in_archive_order":{"model":"MemSum (extractive)","paper_title":"MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes","paper_url":"/paper/memsum-extractive-summarization-of-long","paper_date":"2021-07-19","arxiv_id":"2107.08929","code_links":[{"title":"nianlonggu/memsum","url":"https://github.com/nianlonggu/memsum"}],"syntology":null}},{"leaderboard":"/sota/extractive-text-summarization-on-duc-2004","slug":"extractive-text-summarization-on-duc-2004","dataset":"DUC 2004 Task 1","dataset_url":"/dataset/duc-2004","rows_in_archive":1,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"Abs","paper_title":"A Neural Attention Model for Abstractive Sentence Summarization","paper_url":"/paper/a-neural-attention-model-for-abstractive","paper_date":"2015-09-02","arxiv_id":"1509.00685","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/textsum"},{"title":"toru34/rush_emnlp_2015","url":"https://github.com/toru34/rush_emnlp_2015"},{"title":"Ganeshpadmanaban/Neural-Attention-Model-Abstractive-Summarization","url":"https://github.com/Ganeshpadmanaban/Neural-Attention-Model-Abstractive-Summarization"},{"title":"Ganeshpadmanaban/Neural-Attention-Model","url":"https://github.com/Ganeshpadmanaban/Neural-Attention-Model"}],"syntology":null}},{"leaderboard":"/sota/extractive-text-summarization-on-duc-2004-1","slug":"extractive-text-summarization-on-duc-2004-1","dataset":"DUC 2004","dataset_url":"/dataset/duc-2004","rows_in_archive":1,"metrics":["Test ROGUE-1","Test ROGUE-2"],"first_row_in_archive_order":{"model":"Pre-training-meets-Clustering-A-Hybrid-Extractive-Multi-Document-Summarization-Model","paper_title":"Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model","paper_url":"/paper/pre-training-meets-clustering-a-hybrid","paper_date":"2023-05-25","arxiv_id":null,"code_links":[{"title":"Akankshakarotia/Pre-training-meets-Clustering-A-Hybrid-Extractive-Multi-Document-Summarization-Model","url":"https://github.com/Akankshakarotia/Pre-training-meets-Clustering-A-Hybrid-Extractive-Multi-Document-Summarization-Model"}],"syntology":null}}],"datasets":[{"url":"/dataset/cnn-daily-mail-1","name":"CNN/Daily Mail","full_name":"CNN/Daily Mail","num_papers_in_archive":530},{"url":"/dataset/govreport","name":"GovReport","full_name":"","num_papers_in_archive":83},{"url":"/dataset/duc-2004","name":"DUC 2004","full_name":"DUC 2004","num_papers_in_archive":15},{"url":"/dataset/debatesum","name":"DebateSum","full_name":"","num_papers_in_archive":6},{"url":"/dataset/subsume","name":"SubSumE","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/reader-aware-summarization","name":"Reader-Aware Summarization"}],"parent_tasks":[{"url":"/task/text-summarization","name":"Text Summarization"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":95,"of":95,"of_with_code":34,"tagged_in_all":95,"counts":{"archive_papers_tagged":95,"with_a_code_link":34,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":95,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/get-to-the-point-summarization-with-pointer","slug":"get-to-the-point-summarization-with-pointer","title":"Get To The Point: Summarization with Pointer-Generator Networks","date":"2017-04-14","arxiv_id":"1704.04368","repositories_listed":39,"syntology":{"n":64,"n_ran":30,"n_constructed":11,"n_ran_checked":25,"n_instrument":5,"n_unverified":34,"n_honours":4,"n_violates":2,"n_no_contract":19,"n_pointer_only":44,"phrase":"30 ran (of which 11 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 2 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 34 unverified","sample_list":"/paper/get-to-the-point-summarization-with-pointer#ran","syntology_url":"https://syntology.ai/paper/1704.04368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.04368"}},"official":{"repos":["abisee/pointer-generator"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/text-summarization-with-pretrained-encoders","slug":"text-summarization-with-pretrained-encoders","title":"Text Summarization with Pretrained Encoders","date":"2019-08-22","arxiv_id":"1908.08345","repositories_listed":19,"syntology":{"n":21,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/text-summarization-with-pretrained-encoders#ran","syntology_url":"https://syntology.ai/paper/1908.08345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08345"}},"official":{"repos":["nlpyang/PreSumm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/factorized-attention-self-attention-with","slug":"factorized-attention-self-attention-with","title":"Efficient Attention: Attention with Linear Complexities","date":"2018-12-04","arxiv_id":"1812.01243","repositories_listed":14,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":4,"n_no_contract":1,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/factorized-attention-self-attention-with#ran","syntology_url":"https://syntology.ai/paper/1812.01243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01243"}},"official":{"repos":["cmsflash/efficient-attention"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fine-tune-bert-for-extractive-summarization","slug":"fine-tune-bert-for-extractive-summarization","title":"Fine-tune BERT for Extractive Summarization","date":"2019-03-25","arxiv_id":"1903.10318","repositories_listed":12,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-tune-bert-for-extractive-summarization#ran","syntology_url":"https://syntology.ai/paper/1903.10318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10318"}},"official":{"repos":["nlpyang/BertSum"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/leveraging-bert-for-extractive-text","slug":"leveraging-bert-for-extractive-text","title":"Leveraging BERT for Extractive Text Summarization on Lectures","date":"2019-06-07","arxiv_id":"1906.04165","repositories_listed":8,"syntology":null},{"url":"/paper/a-neural-attention-model-for-abstractive","slug":"a-neural-attention-model-for-abstractive","title":"A Neural Attention Model for Abstractive Sentence Summarization","date":"2015-09-02","arxiv_id":"1509.00685","repositories_listed":4,"syntology":null},{"url":"/paper/debatesum-a-large-scale-argument-mining-and","slug":"debatesum-a-large-scale-argument-mining-and","title":"DebateSum: A large-scale argument mining and summarization dataset","date":"2020-11-14","arxiv_id":"2011.07251","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debatesum-a-large-scale-argument-mining-and#ran","syntology_url":"https://syntology.ai/paper/2011.07251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07251"}},"official":{"repos":["Hellisotherpeople/DebateSum","Hellisotherpeople/debate2vec","arvind-balaji/debate-cards"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aredsum-adaptive-redundancy-aware-iterative","slug":"aredsum-adaptive-redundancy-aware-iterative","title":"AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization","date":"2020-04-13","arxiv_id":"2004.06176","repositories_listed":3,"syntology":null},{"url":"/paper/align-and-attend-multimodal-summarization","slug":"align-and-attend-multimodal-summarization","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","date":"2023-03-13","arxiv_id":"2303.07284","repositories_listed":2,"syntology":null},{"url":"/paper/cx-db8-a-queryable-extractive-summarizer-and","slug":"cx-db8-a-queryable-extractive-summarizer-and","title":"CX DB8: A queryable extractive summarizer and semantic search engine","date":"2020-12-07","arxiv_id":"2012.03942","repositories_listed":2,"syntology":null},{"url":"/paper/screenplay-summarization-using-latent","slug":"screenplay-summarization-using-latent","title":"Screenplay Summarization Using Latent Narrative Structure","date":"2020-04-27","arxiv_id":"2004.12727","repositories_listed":2,"syntology":null},{"url":"/paper/extractive-summarization-as-text-matching","slug":"extractive-summarization-as-text-matching","title":"Extractive Summarization as Text Matching","date":"2020-04-19","arxiv_id":"2004.08795","repositories_listed":2,"syntology":null},{"url":"/paper/searching-for-effective-neural-extractive","slug":"searching-for-effective-neural-extractive","title":"Searching for Effective Neural Extractive Summarization: What Works and What's Next","date":"2019-07-08","arxiv_id":"1907.03491","repositories_listed":2,"syntology":null},{"url":"/paper/tap-dlnd-10-a-corpus-for-document-level","slug":"tap-dlnd-10-a-corpus-for-document-level","title":"TAP-DLND 1.0 : A Corpus for Document Level Novelty Detection","date":"2018-02-20","arxiv_id":"1802.06950","repositories_listed":2,"syntology":null},{"url":"/paper/centroid-based-text-summarization-through","slug":"centroid-based-text-summarization-through","title":"Centroid-based Text Summarization through Compositionality of Word Embeddings","date":"2017-04-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/a-novel-word-pair-based-gaussian-sentence","slug":"a-novel-word-pair-based-gaussian-sentence","title":"A Novel Word Pair-based Gaussian Sentence Similarity Algorithm For Bengali Extractive Text Summarization","date":"2024-11-26","arxiv_id":"2411.17181","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-meets-clustering-a-hybrid","slug":"pre-training-meets-clustering-a-hybrid","title":"Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model","date":"2023-05-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gusum-graph-based-unsupervised-summarization-1","slug":"gusum-graph-based-unsupervised-summarization-1","title":"GUSUM: Graph-based Unsupervised Summarization Using Sentence Features Scoring and Sentence-BERT","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/idn-sum-a-new-dataset-for-interactive-digital","slug":"idn-sum-a-new-dataset-for-interactive-digital","title":"IDN-Sum: A New Dataset for Interactive Digital Narrative Extractive Text Summarisation","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/memsum-extractive-summarization-of-long","slug":"memsum-extractive-summarization-of-long","title":"MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes","date":"2021-07-19","arxiv_id":"2107.08929","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-extractive-summarization-by-pre","slug":"unsupervised-extractive-summarization-by-pre","title":"Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers","date":"2020-10-16","arxiv_id":"2010.08242","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-extractive-summarization-by-pre#ran","syntology_url":"https://syntology.ai/paper/2010.08242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08242"}},"official":{"repos":["xssstory/STAS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/heterogeneous-graph-neural-networks-for-1","slug":"heterogeneous-graph-neural-networks-for-1","title":"Heterogeneous Graph Neural Networks for Extractive Document Summarization","date":"2020-04-26","arxiv_id":"2004.12393","repositories_listed":1,"syntology":null},{"url":"/paper/extractive-multi-document-summarization-using-2","slug":"extractive-multi-document-summarization-using-2","title":"Extractive Multi-document Summarization using K-means, Centroid-based Method, MMR, and Sentence Position","date":"2019-12-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reading-like-her-human-reading-inspired","slug":"reading-like-her-human-reading-inspired","title":"Reading Like HER: Human Reading Inspired Extractive Summarization","date":"2019-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/discourse-aware-neural-extractive-model-for","slug":"discourse-aware-neural-extractive-model-for","title":"Discourse-Aware Neural Extractive Text Summarization","date":"2019-10-30","arxiv_id":"1910.14142","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/discourse-aware-neural-extractive-model-for#ran","syntology_url":"https://syntology.ai/paper/1910.14142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.14142"}},"official":{"repos":["jiacheng-xu/DiscoBERT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/strass-a-light-and-effective-method-for","slug":"strass-a-light-and-effective-method-for","title":"STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings","date":"2019-07-16","arxiv_id":"1907.07323","repositories_listed":1,"syntology":null},{"url":"/paper/neural-extractive-text-summarization-with","slug":"neural-extractive-text-summarization-with","title":"Neural Extractive Text Summarization with Syntactic Compression","date":"2019-02-03","arxiv_id":"1902.00863","repositories_listed":1,"syntology":null},{"url":"/paper/deepchannel-salience-estimation-by","slug":"deepchannel-salience-estimation-by","title":"DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization","date":"2018-11-06","arxiv_id":"1811.02394","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-document-representation-learning","slug":"iterative-document-representation-learning","title":"Iterative Document Representation Learning Towards Summarization with Polishing","date":"2018-09-27","arxiv_id":"1809.10324","repositories_listed":1,"syntology":null},{"url":"/paper/banditsum-extractive-summarization-as-a","slug":"banditsum-extractive-summarization-as-a","title":"BanditSum: Extractive Summarization as a Contextual Bandit","date":"2018-09-25","arxiv_id":"1809.09672","repositories_listed":1,"syntology":null},{"url":"/paper/neural-document-summarization-by-jointly","slug":"neural-document-summarization-by-jointly","title":"Neural Document Summarization by Jointly Learning to Score and Select Sentences","date":"2018-07-06","arxiv_id":"1807.02305","repositories_listed":1,"syntology":null},{"url":"/paper/document-modeling-with-external-attention-for","slug":"document-modeling-with-external-attention-for","title":"Document Modeling with External Attention for Sentence Extraction","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ranking-sentences-for-extractive","slug":"ranking-sentences-for-extractive","title":"Ranking Sentences for Extractive Summarization with Reinforcement Learning","date":"2018-02-23","arxiv_id":"1802.08636","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/ranking-sentences-for-extractive#ran","syntology_url":"https://syntology.ai/paper/1802.08636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08636"}},"official":{"repos":["shashiongithub/Refresh"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/combining-graph-degeneracy-and-submodularity","slug":"combining-graph-degeneracy-and-submodularity","title":"Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scaling-up-summarization-leveraging-large","slug":"scaling-up-summarization-leveraging-large","title":"Scaling Up Summarization: Leveraging Large Language Models for Long Text Extractive Summarization","date":"2024-08-28","arxiv_id":"2408.15801","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixsumm-topic-based-data-augmentation-using","title":"A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches","date":"2024-07-10","arxiv_id":"2407.07341","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranksum-an-unsupervised-extractive-text","title":"RankSum An unsupervised extractive text summarization based on rank fusion","date":"2024-02-07","arxiv_id":"2402.05976","repositories_listed":0,"syntology":null},{"url":null,"slug":"enchancing-semi-supervised-learning-for","title":"Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization","date":"2023-11-16","arxiv_id":"2311.09559","repositories_listed":0,"syntology":null},{"url":null,"slug":"covsumm-an-unsupervised-transformer-cum-graph","title":"CovSumm: an unsupervised transformer-cum-graph-based hybrid document summarization model for CORD-19","date":"2023-04-26","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"san-bert-extractive-summarization-for","title":"San-BERT: Extractive Summarization for Sanskrit Documents using BERT and it's variants","date":"2023-04-04","arxiv_id":"2304.01894","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-informed-proposals-for-discrete","title":"Efficient Informed Proposals for Discrete Distributions via Newton's Series Approximation","date":"2023-02-27","arxiv_id":"2302.13929","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-text-summarization-using","title":"Extractive Text Summarization Using Generalized Additive Models with Interactions for Sentence Selection","date":"2022-12-21","arxiv_id":"2212.10707","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-perspective-scientific-document","title":"Multi Perspective Scientific Document Summarization With Graph Attention Networks (GATS)","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-label-search-for-zero-shot-multi","title":"Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization","date":"2022-04-28","arxiv_id":"2204.13512","repositories_listed":0,"syntology":null},{"url":"/paper/histruct-improving-extractive-text-1","slug":"histruct-improving-extractive-text-1","title":"HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information","date":"2022-03-17","arxiv_id":"2203.09629","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-text-summarization-with-latent","title":"Extractive Text Summarization with Latent Topics using Heterogeneous Graph Neural Network","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gusum-graph-based-unsupervised-summarization","title":"GUSUM: Graph-Based Unsupervised Summarization using Sentence-BERT and Sentence Features","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-extractive-summarization","title":"A New Sentence Extraction Strategy for Unsupervised Extractive Summarization Methods","date":"2021-12-06","arxiv_id":"2112.03203","repositories_listed":0,"syntology":null},{"url":null,"slug":"histruct-improving-extractive-text","title":"HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-pso-ga-for-extractive-text","title":"A Hybrid PSO-GA for Extractive Text Summarization","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/considering-nested-tree-structure-in-sentence","slug":"considering-nested-tree-structure-in-sentence","title":"Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"frame-semantic-enhanced-sentence-modeling-for","title":"Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text Summarization","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monolingual-versus-multilingual-bertology-for","title":"Monolingual versus Multilingual BERTology for Vietnamese Extractive Multi-Document Summarization","date":"2021-08-31","arxiv_id":"2108.13741","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiplex-graph-neural-network-for-extractive","title":"Multiplex Graph Neural Network for Extractive Text Summarization","date":"2021-08-29","arxiv_id":"2108.12870","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-learning-salience-and-redundancy-by","title":"Jointly Learning Salience and Redundancy by Adaptive Sentence Reranking for Extractive Summarization","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-modeling-based-extractive-text","title":"Topic Modeling Based Extractive Text Summarization","date":"2021-06-29","arxiv_id":"2106.15313","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-graph-and-deep-neural-network-for","title":"Knowledge Graph and Deep Neural Network for Extractive Text Summarization by Utilizing Triples","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/neural-extractive-summarization-with","slug":"neural-extractive-summarization-with","title":"Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-neural-text-summarization-using","title":"Improving Neural Text Summarization using Knowledge Graphs","date":"2020-10-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-extractive-text-summarization-with","title":"Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks","date":"2020-10-13","arxiv_id":"2010.06253","repositories_listed":0,"syntology":null},{"url":null,"slug":"multigbs-a-multi-layer-graph-approach-to","title":"MultiGBS: A multi-layer graph approach to biomedical summarization","date":"2020-08-27","arxiv_id":"2008.11908","repositories_listed":0,"syntology":null},{"url":null,"slug":"abstractive-text-summarization-for-sanskrit","title":"Abstractive Text Summarization for Sanskrit Prose: A Study of Methods and Approaches","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-reliable-and-robust-methodology-for","title":"Towards a Reliable and Robust Methodology for Crowd-Based Subjective Quality Assessment of Query-Based Extractive Text Summarization","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-word-embeddings-and-n-grams-for","title":"Combining Word Embeddings and N-grams for Unsupervised Document Summarization","date":"2020-04-25","arxiv_id":"2004.14119","repositories_listed":0,"syntology":null},{"url":null,"slug":"probabilistic-model-of-narratives-over","title":"Probabilistic Model of Narratives Over Topical Trends in Social Media: A Discrete Time Model","date":"2020-04-14","arxiv_id":"2004.06793","repositories_listed":0,"syntology":null},{"url":null,"slug":"at-which-level-should-we-extract-an-empirical","title":"At Which Level Should We Extract? An Empirical Analysis on Extractive Document Summarization","date":"2020-04-06","arxiv_id":"2004.02664","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-memnet-for-extractive-summarization","title":"Hybrid MemNet for Extractive Summarization","date":"2019-12-25","arxiv_id":"1912.11701","repositories_listed":0,"syntology":null},{"url":null,"slug":"unity-in-diversity-learning-distributed","title":"Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization","date":"2019-12-25","arxiv_id":"1912.11688","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-supervised-extractive-text","title":"Towards Supervised Extractive Text Summarization via RNN-based Sequence Classification","date":"2019-11-13","arxiv_id":"1911.06121","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-automatic-extractive-text","title":"Towards automatic extractive text summarization of A-133 Single Audit reports with machine learning","date":"2019-11-08","arxiv_id":"1911.06197","repositories_listed":0,"syntology":null},{"url":"/paper/summary-level-training-of-sentence-rewriting","slug":"summary-level-training-of-sentence-rewriting","title":"Summary Level Training of Sentence Rewriting for Abstractive Summarization","date":"2019-09-19","arxiv_id":"1909.08752","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-semantic-augmentation-of-word","title":"A study of semantic augmentation of word embeddings for extractive summarization","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-topic-based-sentence-representation-for","title":"A topic-based sentence representation for extractive text summarization","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-domain-shift-in-extractive-text","title":"Exploring Domain Shift in Extractive Text Summarization","date":"2019-08-30","arxiv_id":"1908.11664","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-with-fuzzy-hypergraphs-a-topical","title":"Learning with fuzzy hypergraphs: a topical approach to query-oriented text summarization","date":"2019-06-22","arxiv_id":"1906.09445","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-system-for-extractive-clinical-note","title":"A Novel System for Extractive Clinical Note Summarization using EHR Data","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/hibert-document-level-pre-training-of","slug":"hibert-document-level-pre-training-of","title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","date":"2019-05-16","arxiv_id":"1905.06566","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-pre-training-for-hierarchical","title":"Language Model Pre-training for Hierarchical Document Representations","date":"2019-01-26","arxiv_id":"1901.09128","repositories_listed":0,"syntology":null},{"url":null,"slug":"bowler-a-neural-approach-to-extractive-text","title":"BoWLer: A neural approach to extractive text summarization","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"abstractive-text-image-summarization-using","title":"Abstractive Text-Image Summarization Using Multi-Modal Attentional Hierarchical RNN","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/neural-latent-extractive-document","slug":"neural-latent-extractive-document","title":"Neural Latent Extractive Document Summarization","date":"2018-08-22","arxiv_id":"1808.07187","repositories_listed":0,"syntology":null},{"url":null,"slug":"abstractive-and-extractive-text-summarization","title":"Abstractive and Extractive Text Summarization using Document Context Vector and Recurrent Neural Networks","date":"2018-07-20","arxiv_id":"1807.08000","repositories_listed":0,"syntology":null},{"url":"/paper/a-hierarchical-structured-self-attentive","slug":"a-hierarchical-structured-self-attentive","title":"A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)","date":"2018-05-20","arxiv_id":"1805.07799","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-statistical-and-semantic-models-for","title":"Using Statistical and Semantic Models for Multi-Document Summarization","date":"2018-05-11","arxiv_id":"1805.04579","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-text-summarization-using-neural","title":"Extractive Text Summarization using Neural Networks","date":"2018-02-27","arxiv_id":"1802.10137","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-centroid-based-method-a-strong-1","title":"Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-centroid-based-method-a-strong","title":"Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization","date":"2017-08-25","arxiv_id":"1708.07690","repositories_listed":0,"syntology":null},{"url":null,"slug":"extractive-multi-document-summarization-using-1","title":"Extractive Multi Document Summarization using Dynamical Measurements of Complex Networks","date":"2017-08-05","arxiv_id":"1708.01769","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-persian-text-summarization-approach","title":"A New Persian Text Summarization Approach Based on Natural Language Processing and Graph Similarity","date":"2017-02-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classify-or-select-neural-architectures-for","title":"Classify or Select: Neural Architectures for Extractive Document Summarization","date":"2016-11-14","arxiv_id":"1611.04244","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dynamic-programming-algorithm-for-tree","title":"A Dynamic Programming Algorithm for Tree Trimming-based Text Summarization","date":"2015-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-layered-graph-based-multi-document","title":"Multi-layered graph-based multi-document summarization model","date":"2014-05-17","arxiv_id":"1405.7975","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-supervised-bigram-based-ilp-for","title":"Using Supervised Bigram-based ILP for Extractive Summarization","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"using-document-summarization-techniques-for","title":"Using Document Summarization Techniques for Speech Data Subset Selection","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"twitter-topic-summarization-by-ranking-tweets","title":"Twitter Topic Summarization by Ranking Tweets using Social Influence and Content Quality","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/task/extractive-document-summarization/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/extractive-document-summarization/papers/ran/1","json":"/task/extractive-document-summarization/papers/ran/1.json","rows":7}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"060aa75fd351f4b3d8f62eb62d86ab64b5225899ca86fc66bff274ba97b6fede","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}